© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1462
    Prev
    Next
    INDEX
    Explanations

    do not say cancer

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cancer
    -43.00
     cancer
    -42.00
    癌症
    -38.00
     cancers
    -34.00
    癌
    -33.75
    肿瘤
    -26.13
    ancer
    -24.38
     cá
    -22.50
    文化艺术
    -20.00
    致癌
    -20.00
    POSITIVE LOGITS
     arch
    16.00
    mac
    15.81
    _mac
    15.63
    审计
    15.56
     Arch
    15.25
    arch
    15.19
     Formula
    14.75
    Aud
    14.25
    _arch
    14.13
    macros
    14.13
    Activations Density 0.117%

    No Known Activations